Skip to main content
GET
Get Agent Evaluation Run
Read only Get an agent evaluation run to inspect its current progress, result counters, insights, and conversation IDs. Poll this operation after starting a run.

Get Agent Evaluation Run

Use the run ID returned by Start Agent Evaluation Run or List Agent Evaluation Runs.

Minimal request

No request body is needed. Supply the agent ID and run ID.

Evaluation run statuses

A conversation may be queued, calling, judging, scoring, or completed. While calling, its summary can include turns and last_turn; these are live indicators rather than a replacement for the full transcript. Insights have their own status: null until the run completes, then pending, ready, or failed. A completed run can still be waiting for insights.

Verify the result

A 200 response contains the run in data and its conversations list. Use a conversation’s id to inspect its transcript and judgement.

Errors and recovery

404 means the agent or run is not available in this workspace. Check both IDs. Read requests are safe to repeat. Missing, expired, or invalid API credentials return 401. See API authentication.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

id
string
required

Agent ID from List Agents.

runId
string
required

Run ID from Start or List Agent Evaluation Runs.

Response

Successful response.

success
enum<boolean>
required
Available options:
true
error
enum<boolean>
required
Available options:
false
statusCode
integer
required
Example:

200

message
string
required
Example:

"Success"

data
object
required
timestamp
string<date-time>
required